1 / 121

Regularization for Deep Learning

Regularization for Deep Learning. C. Lee Giles. Thanks to Alexander Ororbia and Sargur Srihari. What is Regularization?. Goals of Regularization. Regularize Your Estimator!. regularizer. Regularization & Model Types. The Value of Regularization. Model family. Finding the Best Model.

kscott
Télécharger la présentation

Regularization for Deep Learning

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Regularization for Deep Learning C. Lee Giles Thanks to Alexander Ororbia and Sargur Srihari

  2. What is Regularization?

  3. Goals of Regularization

  4. Regularize Your Estimator! regularizer

  5. Regularization & Model Types

  6. The Value of Regularization Model family

  7. Finding the Best Model

  8. L1 and L2 Unit Balls Unit ball = set of points equidistant to origin Goal = find a way to get to the red line

  9. Dead unit = neuron will never activate on any datapoint again

  10. Augment the data! More robust to adversarial examples

  11. Data augmentation process can be dynamic!

More Related